[MPlayer-dev-eng] [PATCH]: hqdn3d.c: refactorize LowPassMul inmacro, 10%~20% faster on Athlon X2
zhouzongyi at pset.suntec.net
Fri Jan 9 02:51:09 CET 2009
>Since all this is doing is forcing the alignment of LowPassMul could
>your please try the attached patch instead, and tell if it provides
>the same speed-up?
Unfortunately your patch does not bring any speed-up. On Intel CPUs my patch gives less speed-up, ~2%.
And any idea about SIMD optimization on this? I tried SSE2 on deNoiseTemporal but it runs even slower than original C code.
Zhou Zongyi,zhouzongyi at pset.suntec.net
More information about the MPlayer-dev-eng